Images
LLM / IMAGE / VIDEO / AUDIO
Every model.One API.
Build with leading language models. Create images and videos. Connect speech workflows. One gateway, one balance and clear usage-based pricing — from your first experiment to your application.
A prompt. A new possibility.Explore the collection
Create the impossible.
Seedance 2.5 · AI-generated
Current language models
GPT-5.5 · Input $4.5 / 1M tokens
Connect this modelInput · Official $5 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗Start building$10.00 welcome credit for new accounts Try the creative studio
- OpenAI SDK compatible
- Usage-based billing
- No subscription
Language modelsCode, reason and build agentsImage generationCampaigns, portraits and designVideo generationFrom a scene to a moving storyAudio & speechSpeech synthesis and transcription
Browse models & pricingTHE CREATIVE COLLECTION
One idea. A world of possibilities.
Images and films, unexpected worlds and everyday ideas. Find a spark, open the prompt, make something of your own.
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Images
Selected AI-generated examples from GPT Image 2.5 Flare, Gemini 3.1 Flash Image and Seedance 2.5 through Letsllm. Video directions start a new text-to-video creation; live availability and results may differ. Some showcase films use 1080p. Available generation formats and prices are shown with each live model.
The Allgate index
Choose the model.
Know the cost.
Compare capabilities, check the unit price, then create or connect with your chosen model.
26available models
Explore the model referenceShowing 26 / 26 models Available models first · current versions lead
Image
Released 2026-09-08
GPT Image 2.5 Flare image generation with supplier-reported input/output token billing.
- Input
- $6.92316/ 1M tokens
- Output
- $27/ 1M tokens
- Comparison with official pricing
Input · Official — Official rate not verified
Output · Official $30 Save 10%
Official source and date
Standard image output tokens. Text and image input have different official rates and are not compared.
Verified · USD
View official pricing source ↗
Available Create an image
Video
Seedance 2.0 Fast video generation through the documented Let's LLM model ID. Resolution and duration are configurable request parameters.
- Unit price
- $0.1724/ second
- Comparison with official pricing
Different billing units · no direct discount comparison
Official: Output $5.6 · per million tokens
Official source and date
Online list price per million generated video tokens, 480p/720p without video input. Allgate bills per second; units cannot be compared directly.
Verified · USD
View official pricing source ↗
Available Create a video
Video
Seedance 2.0 Mini video generation through the documented Let's LLM model ID. Resolution and duration are configurable request parameters.
- Unit price
- $0.1047/ second
- Comparison with official pricing
Different billing units · no direct discount comparison
Official: Output $3.5 · per million tokens
Official source and date
Online list price per million generated video tokens, 480p/720p without video input. Allgate bills per second; units cannot be compared directly.
Verified · USD
View official pricing source ↗
Available Create a video
Video
Seedance 2.5 video generation through the documented Let's LLM model ID. Resolution and duration are configurable request parameters.
- Unit price
- $0.3231/ second
- Comparison with official pricing
Different billing units · no direct discount comparison
Official: Output $10.7 · per million tokens
Official source and date
Online list price per million generated video tokens, 480p/720p without video input. Allgate bills per second; units cannot be compared directly.
Verified · USD
View official pricing source ↗
Available Create a video
Image
131,072 context
Nano Banana 2 image generation with verified native Gemini transport and reported token usage.
- Input
- $0.45/ 1M tokens
- Output
- $54/ 1M tokens
- Comparison with official pricing
Input · Official $0.5 Save 10%
Output · Official $60 Save 10%
Official source and date
Paid Standard text/image input and image output tokens only; text/thinking output has a separate official rate.
Verified · USD
View official pricing source ↗
Available Create an image
Chat
1,048,576 context
Released 2026-10-13
Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents
- Input
- $1.8/ 1M tokens
- Output
- $9/ 1M tokens
- Comparison with official pricing
Input · Official $2 Save 10%
Output · Official $10 Save 10%
Official source and date
Paid Standard API introductory rates through 2026-11-30; uncached input and text/thinking output.
Verified · USD· Valid until
View official pricing source ↗
Available Connect API
Chat
1,048,576 context
Released 2026-09-02
Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows
- Input
- $0.675/ 1M tokens
- Output
- $3.375/ 1M tokens
- Comparison with official pricing
Input · Official $0.75 Save 10%
Output · Official $3.75 Save 10%
Official source and date
Paid Standard API introductory rates through 2026-12-31; uncached input and text/thinking output.
Verified · USD· Valid until
View official pricing source ↗
Available Connect API
Chat
Released 2026-05-19
Deprecated Gemini product ID; Google now routes this upstream ID to Gemini 3.6 Flash. Choose a current model for new integrations.
- Input
- $0.27/ 1M tokens
- Output
- $2.25/ 1M tokens
- Comparison with official pricing
Official price not verified · discount unavailable
Available Connect API
Chat
1,000,000 context
Claude model for demanding reasoning and long-horizon agentic work
- Input
- $9/ 1M tokens
- Output
- $45/ 1M tokens
- Comparison with official pricing
Input · Official $10 Save 10%
Output · Official $50 Save 10%
Official source and date
Standard Claude API base input/output tokens; caching, tools, batch and regional premiums excluded.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,000,000 context
Fast Claude model for responsive assistance, classification, and lightweight agents
- Input
- $0.09/ 1M tokens
- Output
- $0.45/ 1M tokens
- Comparison with official pricing
Input · Official $0.1 Save 10%
Output · Official $0.5 Save 10%
Official source and date
Standard Claude API, prompts up to 100K tokens; uncached input. Longer prompts use a different official tier.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,000,000 context
Claude model for long-running agentic coding and knowledge work
- Input
- $3.6/ 1M tokens
- Output
- $18/ 1M tokens
- Comparison with official pricing
Input · Official $4 Save 10%
Output · Official $20 Save 10%
Official source and date
Standard Claude API base input/output tokens; caching, tools, batch and regional premiums excluded.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
- Input
- $1.8/ 1M tokens
- Output
- $9/ 1M tokens
- Comparison with official pricing
Input · Official $2 Save 10%
Output · Official $10 Save 10%
Official source and date
Standard Claude API base input/output tokens; caching, tools, batch and regional premiums excluded.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,048,576 context
October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
- Input
- $0.135/ 1M tokens
- Output
- $0.54/ 1M tokens
- Comparison with official pricing
Input · Official $0.15 Save 10%
Output · Official $0.6 Save 10%
Official source and date
Off-peak API, cache-miss input; peak hours cost more. See source for UTC schedule and Chinese public holidays.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
- Input
- $0.594/ 1M tokens
- Output
- $1.782/ 1M tokens
- Comparison with official pricing
Input · Official $0.66 Save 10%
Output · Official $1.98 Save 10%
Official source and date
Off-peak API, cache-miss input; peak hours cost more. See source for UTC schedule and Chinese public holidays.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,000,000 context
Flagship GLM model for long-horizon coding, agents, and complex project delivery
- Input
- $1.26/ 1M tokens
- Output
- $3.96/ 1M tokens
- Comparison with official pricing
Input · Official $1.4 Save 10%
Output · Official $4.4 Save 10%
Official source and date
Standard API uncached input and output tokens; built-in tools and cached input priced separately.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
GLM 5.3 Flash for text generation and visual understanding.
- Input
- $0.135/ 1M tokens
- Output
- $0.45/ 1M tokens
- Comparison with official pricing
Input · Official $0.15 Save 10%
Output · Official $0.5 Save 10%
Official source and date
Standard Z.AI international API uncached input and text output. Cached input, cache storage, tools and taxes are excluded from this comparison.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
GLM 5.3 FlashX for text generation and visual understanding.
- Input
- $0.333/ 1M tokens
- Output
- $1.125/ 1M tokens
- Comparison with official pricing
Input · Official $0.37 Save 10%
Output · Official $1.25 Save 10%
Official source and date
Standard Z.AI international API uncached input and text output. Cached input, cache storage, tools and taxes are excluded from this comparison.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
- Input
- $4.5/ 1M tokens
- Output
- $27/ 1M tokens
- Comparison with official pricing
Input · Official $5 Save 10%
Output · Official $30 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,050,000 context
GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.
- Input
- $9/ 1M tokens
- Output
- $45/ 1M tokens
- Comparison with official pricing
Input · Official $10 Save 10%
Output · Official $50 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,050,000 context
OpenAI's most efficient model for focused, high-volume tasks
- Input
- $0.09/ 1M tokens
- Output
- $0.45/ 1M tokens
- Comparison with official pricing
Input · Official $0.1 Save 10%
Output · Official $0.5 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,050,000 context
OpenAI model for complex coding and agentic workflows
- Input
- $1.8/ 1M tokens
- Output
- $9/ 1M tokens
- Comparison with official pricing
Input · Official $2 Save 10%
Output · Official $10 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,050,000 context
Near-Astra performance for complex coding, computer use, and professional work at a lower cost.
- Input
- $1.8/ 1M tokens
- Output
- $9/ 1M tokens
- Comparison with official pricing
Input · Official $2 Save 10%
Output · Official $10 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
500,000 context
xAI's frontier model for long-running agents, coding, knowledge work, and visual projects
- Input
- $1.8/ 1M tokens
- Output
- $5.4/ 1M tokens
- Comparison with official pricing
Input · Official $2 Save 10%
Output · Official $6 Save 10%
Official source and date
Standard us-east-1 API, up to 200K context; uncached input. Longer context and fast variants cost more.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,048,576 context
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
- Input
- $2.7/ 1M tokens
- Output
- $13.5/ 1M tokens
- Comparison with official pricing
Input · Official $3 Save 10%
Output · Official $15 Save 10%
Official source and date
Standard pay-as-you-go input/output tokens; cache writes, cached input and taxes excluded.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,000,000 context
MiniMax multimodal model for long-context coding, perception, and agent planning
- Input
- $0.27/ 1M tokens
- Output
- $1.08/ 1M tokens
- Comparison with official pricing
Input · Official $0.3 Save 10%
Output · Official $1.2 Save 10%
Official source and date
Standard API, up to 512K input tokens; permanent 50% provider reduction already included. Longer prompts and Priority cost more.
Verified · USD
View official pricing source ↗
Available Connect API
Chat
1,000,000 context
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
- Input
- $1.8/ 1M tokens
- Output
- $5.4/ 1M tokens
- Comparison with official pricing
Input · Official $2 Save 10%
Output · Official $6 Save 10%
Official source and date
Model Studio Singapore International standard list input/output rates; uncached input, promotions excluded.
Verified · USD
View official pricing source ↗
Available Connect API
USD rates. Each model is billed in the unit shown.
Cost calculator
Estimate your monthly token bill.
Pick a model and your monthly token volume. Demo list prices; your invoice is authoritative.
Demo list prices; your invoice is authoritative
Input · Official $2 Save 10%
Output · Official $10 Save 10%
Official source and date
Paid Standard API introductory rates through 2026-11-30; uncached input and text/thinking output.
Verified · USD· Valid until
View official pricing source ↗05Developer experience
Keep your stack.
Change the endpoint.
Keep the OpenAI SDK. Point it at Allgate. Use one key for language and multimodal endpoints, with available models and pricing in the catalogue.
- 01Choose a model
- 02Create a key
- 03Make a request
Keep your SDK. Check parameters and capabilities per model.
allgate / quickstartExample request · not executed
A new destination for your requests
OpenAI-compatible base URL
https://api.allgate.ai/v1# export ALLGATE_API_KEY='YOUR_ALLGATE_API_KEY'curl --fail-with-body 'https://api.allgate.ai/v1/chat/completions' \ -H "Authorization: Bearer $ALLGATE_API_KEY" \ -H "Content-Type: application/json" \ --data-raw '{ "model": "gpt-5.5", "messages": [ { "role": "user", "content": "Hello, Allgate!" } ]}'API reference
Chat CompletionsEach protocol has its own request format.
/v1/chat/completionsResponses/v1/responsesAnthropic Messages/v1/messagesExample model: gpt-5.5Selected from available chat models. Check the catalogue for capabilities and pricing.
Pricing
Pay for usage. No subscription.
Pay by each model’s listed unit; chat separates input and output tokens. Recharge packages and bonuses follow the current configuration.
Live model prices (per 1M tokens)
01 Gemini 4 Argon input $1.80 / 1M output $9.00 / 1M
Gemini 4 Argon input $1.80 / 1M output $9.00 / 1M Input · Official $2 Save 10%
Output · Official $10 Save 10%
Official source and date
Paid Standard API introductory rates through 2026-11-30; uncached input and text/thinking output.
Verified · USD· Valid until
View official pricing source ↗02 GPT Image 2.5 Flare input $6.92316 / 1M output $27.00 / 1M
GPT Image 2.5 Flare input $6.92316 / 1M output $27.00 / 1M Input · Official — Official rate not verified
Output · Official $30 Save 10%
Official source and date
Standard image output tokens. Text and image input have different official rates and are not compared.
Verified · USD
View official pricing source ↗03 Gemini 3.8 Flash input $0.675 / 1M output $3.375 / 1M
Gemini 3.8 Flash input $0.675 / 1M output $3.375 / 1M Input · Official $0.75 Save 10%
Output · Official $3.75 Save 10%
Official source and date
Paid Standard API introductory rates through 2026-12-31; uncached input and text/thinking output.
Verified · USD· Valid until
View official pricing source ↗04 Gemini 3.5 Flash input $0.27 / 1M output $2.25 / 1M
Gemini 3.5 Flash input $0.27 / 1M output $2.25 / 1M Official price not verified · discount unavailable
05 Claude Fable 5.1 input $9.00 / 1M output $45.00 / 1M
Claude Fable 5.1 input $9.00 / 1M output $45.00 / 1M Input · Official $10 Save 10%
Output · Official $50 Save 10%
Official source and date
Standard Claude API base input/output tokens; caching, tools, batch and regional premiums excluded.
Verified · USD
View official pricing source ↗06 Claude Haiku 5.5 input $0.09 / 1M output $0.45 / 1M
Claude Haiku 5.5 input $0.09 / 1M output $0.45 / 1M Input · Official $0.1 Save 10%
Output · Official $0.5 Save 10%
Official source and date
Standard Claude API, prompts up to 100K tokens; uncached input. Longer prompts use a different official tier.
Verified · USD
View official pricing source ↗07 Claude Opus 5.5 input $3.60 / 1M output $18.00 / 1M
Claude Opus 5.5 input $3.60 / 1M output $18.00 / 1M Input · Official $4 Save 10%
Output · Official $20 Save 10%
Official source and date
Standard Claude API base input/output tokens; caching, tools, batch and regional premiums excluded.
Verified · USD
View official pricing source ↗08 Claude Sonnet 5.5 input $1.80 / 1M output $9.00 / 1M
Claude Sonnet 5.5 input $1.80 / 1M output $9.00 / 1M Input · Official $2 Save 10%
Output · Official $10 Save 10%
Official source and date
Standard Claude API base input/output tokens; caching, tools, batch and regional premiums excluded.
Verified · USD
View official pricing source ↗09 DeepSeek V4.1 Flash 1017 input $0.135 / 1M output $0.54 / 1M
DeepSeek V4.1 Flash 1017 input $0.135 / 1M output $0.54 / 1M Input · Official $0.15 Save 10%
Output · Official $0.6 Save 10%
Official source and date
Off-peak API, cache-miss input; peak hours cost more. See source for UTC schedule and Chinese public holidays.
Verified · USD
View official pricing source ↗010 DeepSeek V4 Pro input $0.594 / 1M output $1.782 / 1M
DeepSeek V4 Pro input $0.594 / 1M output $1.782 / 1M Input · Official $0.66 Save 10%
Output · Official $1.98 Save 10%
Official source and date
Off-peak API, cache-miss input; peak hours cost more. See source for UTC schedule and Chinese public holidays.
Verified · USD
View official pricing source ↗011 Gemini 3.1 Flash Image input $0.45 / 1M output $54.00 / 1M
Gemini 3.1 Flash Image input $0.45 / 1M output $54.00 / 1M Input · Official $0.5 Save 10%
Output · Official $60 Save 10%
Official source and date
Paid Standard text/image input and image output tokens only; text/thinking output has a separate official rate.
Verified · USD
View official pricing source ↗012 GLM-5.3 input $1.26 / 1M output $3.96 / 1M
GLM-5.3 input $1.26 / 1M output $3.96 / 1M Input · Official $1.4 Save 10%
Output · Official $4.4 Save 10%
Official source and date
Standard API uncached input and output tokens; built-in tools and cached input priced separately.
Verified · USD
View official pricing source ↗013 GLM 5.3 Flash input $0.135 / 1M output $0.45 / 1M
GLM 5.3 Flash input $0.135 / 1M output $0.45 / 1M Input · Official $0.15 Save 10%
Output · Official $0.5 Save 10%
Official source and date
Standard Z.AI international API uncached input and text output. Cached input, cache storage, tools and taxes are excluded from this comparison.
Verified · USD
View official pricing source ↗014 GLM 5.3 FlashX input $0.333 / 1M output $1.125 / 1M
GLM 5.3 FlashX input $0.333 / 1M output $1.125 / 1M Input · Official $0.37 Save 10%
Output · Official $1.25 Save 10%
Official source and date
Standard Z.AI international API uncached input and text output. Cached input, cache storage, tools and taxes are excluded from this comparison.
Verified · USD
View official pricing source ↗015 GPT-5.5 input $4.50 / 1M output $27.00 / 1M
GPT-5.5 input $4.50 / 1M output $27.00 / 1M Input · Official $5 Save 10%
Output · Official $30 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗016 GPT-6 Astra input $9.00 / 1M output $45.00 / 1M
GPT-6 Astra input $9.00 / 1M output $45.00 / 1M Input · Official $10 Save 10%
Output · Official $50 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗017 GPT-6 Luna input $0.09 / 1M output $0.45 / 1M
GPT-6 Luna input $0.09 / 1M output $0.45 / 1M Input · Official $0.1 Save 10%
Output · Official $0.5 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗018 GPT-6 Sol input $1.80 / 1M output $9.00 / 1M
GPT-6 Sol input $1.80 / 1M output $9.00 / 1M Input · Official $2 Save 10%
Output · Official $10 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗019 GPT-6.1 Sol input $1.80 / 1M output $9.00 / 1M
GPT-6.1 Sol input $1.80 / 1M output $9.00 / 1M Input · Official $2 Save 10%
Output · Official $10 Save 10%
Official source and date
Standard API, up to 272K input tokens; uncached input. Cache, tools, regional and speed-tier premiums excluded.
Verified · USD
View official pricing source ↗020 Grok 4.7 input $1.80 / 1M output $5.40 / 1M
Grok 4.7 input $1.80 / 1M output $5.40 / 1M Input · Official $2 Save 10%
Output · Official $6 Save 10%
Official source and date
Standard us-east-1 API, up to 200K context; uncached input. Longer context and fast variants cost more.
Verified · USD
View official pricing source ↗021 Kimi K3 input $2.70 / 1M output $13.50 / 1M
Kimi K3 input $2.70 / 1M output $13.50 / 1M Input · Official $3 Save 10%
Output · Official $15 Save 10%
Official source and date
Standard pay-as-you-go input/output tokens; cache writes, cached input and taxes excluded.
Verified · USD
View official pricing source ↗022 MiniMax-M3 input $0.27 / 1M output $1.08 / 1M
MiniMax-M3 input $0.27 / 1M output $1.08 / 1M Input · Official $0.3 Save 10%
Output · Official $1.2 Save 10%
Official source and date
Standard API, up to 512K input tokens; permanent 50% provider reduction already included. Longer prompts and Priority cost more.
Verified · USD
View official pricing source ↗023 Qwen3.8 Max input $1.80 / 1M output $5.40 / 1M
Qwen3.8 Max input $1.80 / 1M output $5.40 / 1M Input · Official $2 Save 10%
Output · Official $6 Save 10%
Official source and date
Model Studio Singapore International standard list input/output rates; uncached input, promotions excluded.
Verified · USD
View official pricing source ↗$10.00 in signup credit corresponds to about 111,111,111 input tokens at Claude Haiku 5.5’s input list price. Input-only estimate; output costs are additional.
Top-up options
One balance for language, images, video and audio. No subscription or automatic account RPM/TPM ceiling. Your chosen key budgets and live model availability still apply.
Starter
$10.00 one-time top-up
$10.00 credited after successful payment
Choose a top-upPro
Recommended$100.00 one-time top-up
$100.00 credited after successful payment
Choose a top-upEnterprise
$500.00 one-time top-up
$500.00 credited after successful payment
Choose a top-upPrepaid credit is deducted for actual calls. Paid top-ups and bonuses are recorded separately.
Before you choose a model.
- What is Allgate?
- Allgate is a unified AI model gateway with one API key, prepaid credits and usage records. Connect language models or create with currently available image and video models. Check live supply before choosing audio or retrieval capabilities.
- Which models can I use?
- The public catalogue snapshot dated 2026-10-23 contains 26 model entries, with 26 currently callable. Each detail page shows the model ID, provider, capability, public billing unit and rate. Routing availability can change.
- How do I choose between images, video, language and audio?
- Use Studio to compare image and video generation models. Use the model catalogue for language models and public prices. Audio, embedding and reranking capabilities also depend on the currently published models and routing availability.
Catalogue snapshot: · Public model data · Models and prices · Image and video Studio · API reference
11 FAQ
Questions before you sign up.
Cannot find an answer? Sign in for the docs, or email us directly.
Models come from official or authorised providers. The gateway includes health checks and retries; routing and failover happen inside the gateway.
Each model uses its displayed billing unit; chat usually prices input and output tokens separately. Request records show actual usage and cost, including chargeable partial output.
One balance for language, images, video and audio. No subscription or automatic account RPM/TPM ceiling. Your chosen key budgets and live model availability still apply.
Top-up records and company settlement are supported; contact us for enterprise quotes and invoices.
Requests use channels for your selected model. Usage records and request/response retention depend on platform configuration, account settings and provider policies. Review the privacy policy and provider terms.
Activated Free and Paid accounts have equal account throughput. Explicit key limits and supplier capabilities still apply. Switch models using the exact catalogue ID and the endpoint for its category.
Get started
Bring model capabilities into your project.
Choose a model, configure your project and verify your first API call. Pay for actual usage.
Pay as you go · Verify a real call in the workbench